# SEE: Strategic Exploration and Exploitation for Cohesive In-Context Prompt Optimization

arXiv: https://arxiv.org/abs/2402.11347 · HTML: https://mlsanity.com/paper/2402.11347/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Feb 2024.

## Built on by (most cited first, 12 of 12)

- [Efficient Prompting Methods for Large Language Models: A Survey](https://mlsanity.com/paper/2404.01077/) (2024)
- [Prompt Optimization with EASE? Efficient Ordering-aware Automated Selection of Exemplars](https://mlsanity.com/paper/2405.16122/) (2024)
- [Multimodal Prompt Optimization: Why Not Leverage Multiple Modalities for MLLMs](https://mlsanity.com/paper/2510.09201/) (2025)
- [Synthetic Interaction Data for Scalable Personalization in Large Language Models](https://mlsanity.com/paper/2602.12394/) (2026)
- [RIMRULE: Improving Tool-Using Language Agents via MDL-Guided Rule Learning](https://mlsanity.com/paper/2601.00086/) (2025)
- [Beyond Elicitation: Provision-based Prompt Optimization for Knowledge-Intensive Tasks](https://mlsanity.com/paper/2511.10465/) (2025)
- [Automated Summarization of Software Documents: An LLM-based Multi-Agent Approach](https://mlsanity.com/paper/2606.24689/) (2026)
- [From Many to Meaningful: Feature-Guided Zero-Shot Chronic Kidney Disease Screening Using Large Language Models](https://mlsanity.com/paper/2607.12260/) (2026)
- [Search-Based Software Engineering and AI Foundation Models: Current Landscape and Future Roadmap](https://mlsanity.com/paper/2505.19625/) (2025)
- [FitText: Evolving Agent Tool Ecologies via Memetic Retrieval](https://mlsanity.com/paper/2605.02411/) (2026)
- [PA-CoT: Profile-Adaptive Chain-of-Thought for Personalized Nutritional Consulting](https://mlsanity.com/paper/2608.24907/) (2026)
- [StraTune: Adaptive Selection of Revision Operators for Self-Evolving LLM Skills](https://mlsanity.com/paper/2609.32886/) (2026)

## Abstract (arXiv)

Designing optimal prompts for Large Language Models (LLMs) is a complicated and resource-intensive task, often requiring substantial human expertise and effort. Existing approaches typically separate the optimization of prompt instructions and in-context learning examples, leading to incohesive prompts that are defined and represented by suboptimal task performance. To overcome these challenges, we propose a novel Cohesive In-Context Prompt Optimization framework that refines both prompt instructions and examples. However, formulating such an optimization in the discrete and high-dimensional space of natural language poses significant challenges in both convergence and computational efficiency. To address these issues, we introduce SEE, a scalable and efficient prompt optimization framework that adopts metaheuristic optimization principles and strategically balances exploration and exploitation to enhance optimization performance and achieve efficient convergence. SEE features a quad-phased design that alternates between global traversal (exploration) and local optimization (exploitation) and adaptively chooses LLM operators during the optimization process. We have conducted a comprehensive evaluation across 35 benchmark tasks, and SEE significantly outperforms state-of-the-art baseline methods by a large margin, achieving an average performance gain of 13.94 while reducing computational costs by 58.67.